hypergraph

HyperAgent is a research framework that models tool relations via a Tool-Schema Hypergraph to improve planning and execution for LLM agents, reducing API calls and token usage on the AppWorld benchmark.

StyleForge introduces a scene-level structured selection framework for fixed-layout indoor furniture styling, using a dynamic hypergraph style field and counterfactual style preference learning to improve furniture retrieval and style coherence on 3D-FRONT.

HyCE-RAG is a novel hypergraph-based retrieval-augmented generation framework for multi-hop question answering that constructs explicit evidence chains via confidence-aware heuristic search, outperforming standard RAG and graph-based RAG methods in accuracy, relevance, and faithfulness.

MissHyper is a new hypergraph forecasting model that restores clinical synchronicity by aggregating co-timestamp records before message passing, achieving consistent gains on PhysioNet 2012, MIMIC-III, and MIMIC-IV benchmarks.

This paper proposes improvements to HyperGraphRAG by using self-consistency prompting for better fact extraction and Personalized PageRank for enhanced chunk retrieval.

This paper presents IsalHG, a method to represent any finite connected hypergraph as a string over a compact instruction alphabet, decoded by a virtual machine. It introduces a canonical string conjecture for hypergraph isomorphism and benchmarks against established methods.

This paper introduces GRAFT, a curated multimodal dataset linking gene expression profiles and phenotypic traits in Arabidopsis thaliana, along with graph and hypergraph benchmarks for phenotype prediction. It aims to advance genome-to-phenome mapping in plant biology.

HyPE introduces a hypergraph-based persona encoder that models high-order relations among persona attributes via category-aware hyperedges and persistent edge embeddings, achieving consistent improvements over flat pooling baselines on PersonaChat across multiple backbone models.

HyperPatch proposes a parameter-preserving framework for sequential knowledge editing under n-ary structural drift, using hypergraph neural networks to maintain event integrity. It achieves 96.24% and 21.06% relative improvements in Hop-wise Accuracy on MQuAKE-CF and MQuAKE-T benchmarks, respectively.

Introduces GHI, a Graphormer-over-conditioned-hypergraph-incidence framework for aspect-based sentiment analysis that represents linguistic evidence as token–hyperedge incidence relations, achieving state-of-the-art results on six benchmarks with only 247M parameters.

This paper proposes Hyper-Align, a framework that serializes hypergraph structures into tokens via HIDT-O and HIP, enabling LLMs to process high-order relationships, and introduces HyperAlign-Bench for evaluation.

Aperio is a programming language designed to reduce the translation cost between human mental models and LLM code generation by using a structural model based on recursive hypergraphs of typed units called loci.

HEAR is an enterprise agentic reasoner using a Stratified Hypergraph Ontology to perform multi-hop reasoning over heterogeneous business systems, achieving up to 94.7% accuracy on supply-chain tasks.